{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ORUDY2VCW3NXDIG75PSNZF6JJR","short_pith_number":"pith:ORUDY2VC","canonical_record":{"source":{"id":"2204.08121","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T01:30:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"11166d2dd0f5ffbef882dfddf5024def4a15c7f1d1c857156fd52c1025d68d02","abstract_canon_sha256":"52888a308788e45c0c3cddbf152208e394fd7afd6307192a86278d17ad859ade"},"schema_version":"1.0"},"canonical_sha256":"74683c6aa2b6db71a0dfebe4dc97c94c762cdd0f57f8ccf7d667e11463c18bdf","source":{"kind":"arxiv","id":"2204.08121","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08121","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08121v2","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08121","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"pith_short_12","alias_value":"ORUDY2VCW3NX","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"pith_short_16","alias_value":"ORUDY2VCW3NXDIG7","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"pith_short_8","alias_value":"ORUDY2VC","created_at":"2026-07-05T04:58:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ORUDY2VCW3NXDIG75PSNZF6JJR","target":"record","payload":{"canonical_record":{"source":{"id":"2204.08121","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T01:30:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"11166d2dd0f5ffbef882dfddf5024def4a15c7f1d1c857156fd52c1025d68d02","abstract_canon_sha256":"52888a308788e45c0c3cddbf152208e394fd7afd6307192a86278d17ad859ade"},"schema_version":"1.0"},"canonical_sha256":"74683c6aa2b6db71a0dfebe4dc97c94c762cdd0f57f8ccf7d667e11463c18bdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:03.599476Z","signature_b64":"uQr4aYiS85E1ApEp+I3PFWGCXocWLNmkFWE9/uUxts/C1NIGOZ5zNB9tuSBrmcXazfowv253z1+tRg9HAZUXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74683c6aa2b6db71a0dfebe4dc97c94c762cdd0f57f8ccf7d667e11463c18bdf","last_reissued_at":"2026-07-05T04:58:03.599003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:03.599003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.08121","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:58:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3eZ3WK2YVXwPol38qnp40OXkwB/6vpEMV9r3TszCcobhE3xCdhxMf5dIoRdnJOV/lkZYC36iNls9YtykpxGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T09:34:56.664244Z"},"content_sha256":"3d53896632d1e24d504905837afb23f432cc5599b4519a2bdc4744afa3fb67b1","schema_version":"1.0","event_id":"sha256:3d53896632d1e24d504905837afb23f432cc5599b4519a2bdc4744afa3fb67b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ORUDY2VCW3NXDIG75PSNZF6JJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-end Dense Video Captioning as Sequence Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ashish V. Thapliyal, Bo Pang, Radu Soricut, Wanrong Zhu, William Yang Wang","submitted_at":"2022-04-18T01:30:54Z","abstract_excerpt":"Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes a segment for each event, then renders a caption for each identified segment. Recent advances in large-scale sequence generation pretraining have seen great success in unifying task formulation for a great variety of tasks, but so far, more complex tasks such as dense video captioning are not able to fully utilize this powerful paradigm. In this work, we show how to model the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08121","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.08121/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:58:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cjQkEq48JxzyFexE2lR3Gr9So3Q8U0yA2zj12hxmAfGooH3S/Nr6LqEGsmxaPjr/Rh8q4g4OUT96PdnxPUtPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T09:34:56.664651Z"},"content_sha256":"d1a22dd455ca93d39154ec7f62708b2909aa020a6604515bec46af044107e2d7","schema_version":"1.0","event_id":"sha256:d1a22dd455ca93d39154ec7f62708b2909aa020a6604515bec46af044107e2d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORUDY2VCW3NXDIG75PSNZF6JJR/bundle.json","state_url":"https://pith.science/pith/ORUDY2VCW3NXDIG75PSNZF6JJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORUDY2VCW3NXDIG75PSNZF6JJR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-25T09:34:56Z","links":{"resolver":"https://pith.science/pith/ORUDY2VCW3NXDIG75PSNZF6JJR","bundle":"https://pith.science/pith/ORUDY2VCW3NXDIG75PSNZF6JJR/bundle.json","state":"https://pith.science/pith/ORUDY2VCW3NXDIG75PSNZF6JJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORUDY2VCW3NXDIG75PSNZF6JJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ORUDY2VCW3NXDIG75PSNZF6JJR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"52888a308788e45c0c3cddbf152208e394fd7afd6307192a86278d17ad859ade","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T01:30:54Z","title_canon_sha256":"11166d2dd0f5ffbef882dfddf5024def4a15c7f1d1c857156fd52c1025d68d02"},"schema_version":"1.0","source":{"id":"2204.08121","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08121","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08121v2","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08121","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"pith_short_12","alias_value":"ORUDY2VCW3NX","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"pith_short_16","alias_value":"ORUDY2VCW3NXDIG7","created_at":"2026-07-05T04:58:03Z"},{"alias_kind":"pith_short_8","alias_value":"ORUDY2VC","created_at":"2026-07-05T04:58:03Z"}],"graph_snapshots":[{"event_id":"sha256:d1a22dd455ca93d39154ec7f62708b2909aa020a6604515bec46af044107e2d7","target":"graph","created_at":"2026-07-05T04:58:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.08121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes a segment for each event, then renders a caption for each identified segment. Recent advances in large-scale sequence generation pretraining have seen great success in unifying task formulation for a great variety of tasks, but so far, more complex tasks such as dense video captioning are not able to fully utilize this powerful paradigm. In this work, we show how to model the t","authors_text":"Ashish V. Thapliyal, Bo Pang, Radu Soricut, Wanrong Zhu, William Yang Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T01:30:54Z","title":"End-to-end Dense Video Captioning as Sequence Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08121","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3d53896632d1e24d504905837afb23f432cc5599b4519a2bdc4744afa3fb67b1","target":"record","created_at":"2026-07-05T04:58:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"52888a308788e45c0c3cddbf152208e394fd7afd6307192a86278d17ad859ade","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T01:30:54Z","title_canon_sha256":"11166d2dd0f5ffbef882dfddf5024def4a15c7f1d1c857156fd52c1025d68d02"},"schema_version":"1.0","source":{"id":"2204.08121","kind":"arxiv","version":2}},"canonical_sha256":"74683c6aa2b6db71a0dfebe4dc97c94c762cdd0f57f8ccf7d667e11463c18bdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74683c6aa2b6db71a0dfebe4dc97c94c762cdd0f57f8ccf7d667e11463c18bdf","first_computed_at":"2026-07-05T04:58:03.599003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:03.599003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQr4aYiS85E1ApEp+I3PFWGCXocWLNmkFWE9/uUxts/C1NIGOZ5zNB9tuSBrmcXazfowv253z1+tRg9HAZUXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:03.599476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08121","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d53896632d1e24d504905837afb23f432cc5599b4519a2bdc4744afa3fb67b1","sha256:d1a22dd455ca93d39154ec7f62708b2909aa020a6604515bec46af044107e2d7"],"state_sha256":"53a4b18d0679a0490138d87d15c912d10a51864682ff0b3b8358c46b1d755a7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNGJq1KbkNP+Ya6knQuMQJdVVvYgSNQkeYxJTwGUBUGU1Xh9Rpu5Q5fXyg5ecJpupC/69THKsCVycuY50si0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T09:34:56.667326Z","bundle_sha256":"22bd6796e54b07d1565e6123861f9c643f0ee264d41714719e1319b4d8876ee5"}}